Medical image captioning automatically generates a medical description to describe the content of a given medical image . A traditional medical imagecaptioning model creates a . medical description only based on a single medical image input . A newend-to-end deep multi-modal medical image caption . model is . effective with the increase of +53.2% in BLEU-avg and +18.6% in CIDEr, compared with the state-of-the-art method . The proposed model is effective with . an increase in the effectiveness of the current method of captioning, compared . with the existing . model, according to the . experimental results show that the proposed model was effective with an .increase of + 53.2 percent in B LEU-AVg and . + 18.6 percent in

Author(s) : Jia-Hong Huang, Ting-Wei Wu, Marcel Worring

Links : PDF - Abstract

Code :

https://github.com/menajosep/AleatoricSent


Coursera

Keywords : medical - image - model - increase - captioning -

Leave a Reply

Your email address will not be published. Required fields are marked *